Rental capacity · price floors · API margins

Rentable GPU market monitor

Live

Loading latest sweep…

Market now

Modeled opportunity

Total confirmed H100-equivalent capacity

Provider-reported units × G_n · UTC

Confirmed lower bound only. Solid lines are complete exact observations; dashed bridges cross intervals without one. Unknown inventory is never plotted as zero.

Planning margin vs API markets

Live rented capacity · OpenRouter context gate · current SiliconFlow + AIHubMix quotes

Model	Market endpoint	Modeled rental cost	G_n delivery	Margin range	Base margin	Break-even rent	Decision

Weekly open-weight candidate audit

Awaiting OpenRouter and GPU price snapshots.

Prompt-cache discounts by provider and model

Live selected routes · follows the model selector above · missing price ≠ zero discount

Agent-session hit-rate sensitivity

Select a model to compare steady-state cache reads.

Cache-hit share	Effective API input $/M	API savings	Modeled self-host input $/M	Input margin

Route / provider	Model	Input $/M	Cache read $/M	Read discount	Cache write $/M	Write premium	Mode

Steady-state read scenarios only. Cache-write charges, TTL/eviction, and the real traffic-wide hit share are not amortized. Self-host cache cost appears only after a matched warm-prefix benchmark. Missing published cache price is unavailable, not zero.

Benchmark next: exact stock

Available classes still missing a full precision profile

Prioritized from exact inventory: validate the SKU, rent the cheapest confirmed offer, then require two clean benchmark runs. Stock is a lower bound, not a reservation.

External rental benchmarks

Settled reference rates versus confirmed provider floors

GPU	Ornn OCPI	Silicon NeoCloud	Silicon hyperscaler	Raw provider floor	GPU Tracker floor	Tracker listings	Latest index date

Shows externally indexed GPUs by default. Expand only when comparing tracker-only listings. Reference rates remain separate from executable offers.

Compute-price forward signal

Kalshi monthly-average contracts · not rentable GPU stock

What it coversFive GPU price indices, not five physical GPUs. Each contract settles on one GPU model's monthly average USD/GPU-hour.

How to read odds“YES 72% at >$3” means the market price implies roughly a 72% chance of settling above $3. It is not a calibrated forecast.

How to use itCompare the median bracket with Ornn now. Higher suggests future scarcity; lower suggests waiting may pay. Use directionally, not as a rental quote.

GPU	Settlement month	Median price bracket	Ornn now	Implied move	Crossing odds	Volume	Open interest

View full contract ladders

GPU	Tenor	Contract	Best YES bid	Best YES ask	Last	Volume	Open interest

The median bracket spans adjacent strikes where YES midpoint odds cross 50%; its midpoint is compared with Ornn only for intuition, not presented as an expected price. Volume is contracts traded; open interest is outstanding contracts—neither measures GPUs or dollars. Spreads, fees, liquidity, and risk premia can distort probability-like prices.

Confirmed capacity by GPU class

Physical stock × G_n · H100 equivalents

Confirmed lower bound only: provider-reported units × G_n. Unknown stock is excluded, never assumed to be one or zero.

Confirmed capacity by provider

Current and time-weighted H100 equivalents

Exact provider-reported quantities only. “Quantity unknown” providers may have rentable inventory, but are excluded from H100e totals until their API exposes a defensible quantity or lower bound.

Price / G_n ranking

Qualified known capacity

Rank								Raw 7d

Rank = Σ(price × known units) ÷ Σ(known units) ÷ measured G_n. Raw floor is shown separately and never sets rank. Clore requires ≥95% reliability, ≥4.0 rating, and ≥5 ratings; unknown-unit offers are excluded. Host throttling remains unknown until measured; estimated G_n rows are unranked.

Provider network

Latest collection state

Providers needing credentials

Measured precision throughput

Dense GEMM throughput · TOPS

							INT4

Measured matrix: 8192×8192 GEMM, 50 iterations. INT4 is not collected: the harness has no validated packed-INT4 kernel. NVFP4 is capability-gated and preserves unsupported/failed status. G_n ranking uses accepted BF16 throughput.

Margin methodology

What is compared, what is measured, and why API prices can beat public GPU rent

Planning model

Headline margin

The headline pools an equal one-million-token workload for every quoted model; it is not traffic-weighted because provider traffic shares are unavailable. A negative headline does not mean every model is negative.

margin = (API revenue − modeled GPU cost) ÷ API revenue

API revenue

OpenRouter uses the cheapest live endpoint with matching precision and at least 95% one-day uptime. Revenue blends standard input/output prices at the configured token mix. AIHubMix and SiliconFlow use their cheapest listed matching quote.

revenue = 80% input price + 20% output price

GPU cost

Each model gets its own capacity-weighted blend of qualified live rental stock. Eligible cards need a public price, measured G_n, compatible weights, and room for one full advertised-context KV/state cache.

cost = rent × 1.10 overhead ÷ throughput ÷ 70% billable utilization

G_n delivery gap

Calibrated capacity is the measured BF16 dense-compute reference for one H100-equivalent hour. Benchmark-realized work converts the matched model's best measured input/output serving rates into G_n using its 2 × active-parameter sticker and the declared token mix.

gap = 1 − benchmark-realized Gₙ/hour ÷ calibrated Gₙ/hour

Example: an 84.27% gap means the benchmark delivered 15.73% of calibrated capacity as model-token work. The remainder reflects model/runtime delivery limits such as memory movement, attention, KV-cache traffic, kernel shapes, and serial decode. It is not 84.27% GPU idle time and does not measure production fleet utilization or idle lease time.

Prompt caching

Not included in the headline. The table compares published route-level input, cache-read, and cache-write prices. Missing cache prices stay unavailable, never zero. Hit-rate rows blend cold input and steady-state reads; they exclude initial writes, TTL/eviction, and reuse distribution because providers do not publish a traffic-wide hit share. Warm self-host cost appears only after the exact model, quantization, GPU, full context, repeated prefix, and vLLM cache counters are measured.

read discount = 1 − cache-read price ÷ input price
effective input = (1 − hit share) × input + hit share × cache read

Why API prices can be lower

Our cost basis is public on-demand rental economics. API providers may own or reserve hardware, use TPUs or undisclosed GPUs, batch more requests, sustain higher utilization, reuse prefixes, or price below public rental cost. This is not asserted to be like-for-like hardware.

Evidence and uncertainty

Loading benchmark coverage…

Full-context session counts are memory ceilings, not measured concurrency. Sensitivity ranges vary efficiency, utilization, and overhead; they are not confidence intervals. AIHubMix units remain unvalidated.

API market	Models	Benchmarked	Current pooled margin	Weighting